{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T08:51:14Z","timestamp":1791449474479,"version":"4.3.3"},"reference-count":77,"publisher":"SAGE Publications","issue":"4","license":[{"start":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T00:00:00Z","timestamp":1772496000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Stat Methods Med Res"],"published-print":{"date-parts":[[2026,4]]},"abstract":"<jats:p>Motivated by recent development of tensor regression modeling, we propose a novel tensor ensemble learning (TEL) approach. While CANDECOMP\/PARAFAC (CP) decomposition is an efficient technique to reduce the number of parameters in tensor covariate, determining an appropriate CP rank remains uncertain in practice. Furthermore, the structural complexity of tensor often varies across different spatial regions. To explore the intrinsic tensor structure, we design different tensor partition strategies and divide tensor into disjoint blocks to form candidate models. A model ensemble method is then developed to explore the uncertainty in both tensor block structure and CP rank. To assign weights to candidate models and enhance predictive performance, we leverage the predictability, computability, and stability framework for veridical data science. Simulation studies are carried out to assess the performance of TEL under varying levels of tensor complexity. We further apply TEL to two real data applications about glaucoma management using fundus image and cognitive ability prediction in Alzheimer\u2019s disease using neuroimaging. Our numerical studies illustrate the superiority of TEL over existing methods and highlight its promise for complex tensor data analysis.<\/jats:p>","DOI":"10.1177\/09622802261424654","type":"journal-article","created":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T18:41:24Z","timestamp":1773254484000},"page":"847-866","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":0,"title":["An ensemble approach to tensor learning"],"prefix":"10.1177","volume":"35","author":[{"given":"Jiaxin","family":"He","sequence":"first","affiliation":[{"name":"National University of Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9704-4135","authenticated-orcid":false,"given":"Jialiang","family":"Li","sequence":"additional","affiliation":[{"name":"National University of Singapore"},{"name":"Duke University NUS Graduate Medical School, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","published-online":{"date-parts":[[2026,3,3]]},"reference":[{"key":"e_1_3_3_2_2","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2013.776499"},{"key":"e_1_3_3_3_2","doi-asserted-by":"publisher","DOI":"10.1007\/s12561-018-9215-6"},{"key":"e_1_3_3_4_2","doi-asserted-by":"publisher","DOI":"10.1214\/17-AOAS1116"},{"key":"e_1_3_3_5_2","unstructured":"Si Y Zhang Y Cai Y et al. An efficient tensor regression for high-dimensional data. arXiv preprint arXiv:220513734 2022."},{"key":"e_1_3_3_6_2","doi-asserted-by":"publisher","DOI":"10.1214\/23-AOAS1830"},{"key":"e_1_3_3_7_2","first-page":"1","article-title":"Dynamic tensor recommender systems","volume":"22","author":"Zhang Y","year":"2021","unstructured":"Zhang Y, Bi X, Tang N, et al. Dynamic tensor recommender systems. J Mach Learn Rse 2021; 22: 1\u201335.","journal-title":"J Mach Learn Rse"},{"key":"e_1_3_3_8_2","doi-asserted-by":"publisher","DOI":"10.1214\/17-AOS1659"},{"key":"e_1_3_3_9_2","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2021.1912757"},{"key":"e_1_3_3_10_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jeconom.2023.105544"},{"key":"e_1_3_3_11_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-023-02424-4"},{"key":"e_1_3_3_12_2","doi-asserted-by":"publisher","DOI":"10.1111\/biom.13743"},{"key":"e_1_3_3_13_2","doi-asserted-by":"publisher","DOI":"10.1080\/10618600.2017.1401544"},{"key":"e_1_3_3_14_2","doi-asserted-by":"publisher","DOI":"10.1137\/07070111X"},{"key":"e_1_3_3_15_2","doi-asserted-by":"publisher","DOI":"10.1137\/19M126476X"},{"key":"e_1_3_3_16_2","doi-asserted-by":"publisher","DOI":"10.1137\/19M1299335"},{"key":"e_1_3_3_17_2","first-page":"18274","article-title":"Low-rank tensor estimation via riemannian Gauss-Newton: statistical optimality and second-order convergence","volume":"24","author":"Luo Y","year":"2023","unstructured":"Luo Y, Zhang AR. Low-rank tensor estimation via riemannian Gauss-Newton: statistical optimality and second-order convergence. J Mach Learn Res 2023; 24: 18274\u201318321.","journal-title":"J Mach Learn Res"},{"key":"e_1_3_3_18_2","doi-asserted-by":"publisher","DOI":"10.1137\/090752286"},{"key":"e_1_3_3_19_2","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-statistics-042720-020816"},{"key":"e_1_3_3_20_2","first-page":"84","article-title":"Foundations of the parafac procedure: models and conditions for an \u201cexplanatory\u201d multi-modal factor analysis","volume":"16","author":"Harshman RA","year":"1970","unstructured":"Harshman RA. Foundations of the parafac procedure: models and conditions for an \u201cexplanatory\u201d multi-modal factor analysis. UCLA Work Paper Phonet 1970; 16: 84.","journal-title":"UCLA Work Paper Phonet"},{"key":"e_1_3_3_21_2","first-page":"1","article-title":"Bayesian tensor regression","volume":"18","author":"Guhaniyogi R","year":"2017","unstructured":"Guhaniyogi R, Qamar S, Dunson DB. Bayesian tensor regression. J Mach Learn Res 2017; 18: 1\u201331.","journal-title":"J Mach Learn Res"},{"key":"e_1_3_3_22_2","first-page":"1","article-title":"Improving tensor regression by optimal model averaging","volume":"0","author":"Bu Q","year":"2024","unstructured":"Bu Q, Liang H, Zhang X, et al. Improving tensor regression by optimal model averaging. J Am Stat Assoc 2024; 0: 1\u201321.","journal-title":"J Am Stat Assoc"},{"key":"e_1_3_3_23_2","doi-asserted-by":"publisher","DOI":"10.1198\/jasa.2009.tm08439"},{"key":"e_1_3_3_24_2","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2014.983233"},{"key":"e_1_3_3_25_2","first-page":"1150","article-title":"Supervised multiway factorization","volume":"12","author":"Lock EF","year":"2018","unstructured":"Lock EF, Li G. Supervised multiway factorization. Electr J Stat 2018; 12: 1150.","journal-title":"Electr J Stat"},{"key":"e_1_3_3_26_2","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2019.1585254"},{"key":"e_1_3_3_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/2512329"},{"key":"e_1_3_3_28_2","first-page":"1","article-title":"Sparse tensor additive regression","volume":"22","author":"Hao B","year":"2021","unstructured":"Hao B, Wang B, Wang P, et al. Sparse tensor additive regression. J Mach Learn Rse 2021; 22: 1\u201343.","journal-title":"J Mach Learn Rse"},{"key":"e_1_3_3_29_2","first-page":"1","article-title":"High-dimensional quantile tensor regression","volume":"21","author":"Lu W","year":"2020","unstructured":"Lu W, Zhu Z, Lian H. High-dimensional quantile tensor regression. J Mach Learn Res 2020; 21: 1\u201331.","journal-title":"J Mach Learn Res"},{"key":"e_1_3_3_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2022.3198725"},{"key":"e_1_3_3_31_2","first-page":"1","article-title":"Soft tensor regression","volume":"22","author":"Papadogeorgou G","year":"2021","unstructured":"Papadogeorgou G, Zhang Z, Dunson DB. Soft tensor regression. J Mach Learn Res 2021; 22: 1\u201353.","journal-title":"J Mach Learn Res"},{"key":"e_1_3_3_32_2","doi-asserted-by":"publisher","DOI":"10.1111\/rssb.12547"},{"key":"e_1_3_3_33_2","doi-asserted-by":"publisher","DOI":"10.1093\/jrsssb\/qkad024"},{"key":"e_1_3_3_34_2","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/asad049"},{"key":"e_1_3_3_35_2","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1995.tb02015.x"},{"key":"e_1_3_3_36_2","doi-asserted-by":"publisher","DOI":"10.2307\/2983440"},{"key":"e_1_3_3_37_2","doi-asserted-by":"publisher","DOI":"10.1080\/07350015.2020.1870479"},{"key":"e_1_3_3_38_2","doi-asserted-by":"publisher","DOI":"10.1002\/sim.9819"},{"key":"e_1_3_3_39_2","doi-asserted-by":"publisher","DOI":"10.2307\/2533961"},{"key":"e_1_3_3_40_2","doi-asserted-by":"publisher","DOI":"10.1111\/j.1468-0262.2007.00785.x"},{"key":"e_1_3_3_41_2","first-page":"661","article-title":"Some comments on CP","volume":"15","author":"Mallows CL","year":"1973","unstructured":"Mallows CL. Some comments on CP. Technometrics 1973; 15: 661\u2013675.","journal-title":"Technometrics"},{"key":"e_1_3_3_42_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jeconom.2009.10.030"},{"key":"e_1_3_3_43_2","doi-asserted-by":"publisher","DOI":"10.1198\/jasa.2011.tm09478"},{"key":"e_1_3_3_44_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jeconom.2011.06.019"},{"key":"e_1_3_3_45_2","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2019.1604363"},{"key":"e_1_3_3_46_2","doi-asserted-by":"publisher","DOI":"10.1093\/jrsssb\/qkae094"},{"key":"e_1_3_3_47_2","doi-asserted-by":"publisher","DOI":"10.1080\/07474938.2023.2280825"},{"key":"e_1_3_3_48_2","doi-asserted-by":"publisher","DOI":"10.1177\/09622802231154327"},{"key":"e_1_3_3_49_2","doi-asserted-by":"publisher","DOI":"10.1080\/10485252.2025.2464796"},{"key":"e_1_3_3_50_2","doi-asserted-by":"publisher","DOI":"10.1080\/10485252.2023.2215339"},{"key":"e_1_3_3_51_2","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2013.838168"},{"key":"e_1_3_3_52_2","doi-asserted-by":"publisher","DOI":"10.1198\/016214505000000088"},{"key":"e_1_3_3_53_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.csda.2013.05.008"},{"key":"e_1_3_3_54_2","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2015.1115762"},{"key":"e_1_3_3_55_2","doi-asserted-by":"publisher","DOI":"10.1111\/rssc.12502"},{"key":"e_1_3_3_56_2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022648800760"},{"key":"e_1_3_3_57_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(05)80023-1"},{"key":"e_1_3_3_58_2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1018054314350"},{"key":"e_1_3_3_59_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-9326-7"},{"key":"e_1_3_3_60_2","volume-title":"Better Deep Learning: Train Faster, Reduce Overfitting, and Make Better Predictions","author":"Brownlee J","year":"2018","unstructured":"Brownlee J. Better Deep Learning: Train Faster, Reduce Overfitting, and Make Better Predictions. San Juan, Puerto Rico: Machine learning mastery, 2018."},{"key":"e_1_3_3_61_2","volume-title":"Veridical data science: The practice of responsible data analysis and decision making","author":"Yu B","year":"2024","unstructured":"Yu B, Barter RL. Veridical data science: The practice of responsible data analysis and decision making. Cambridge, MA: MIT Press, 2024."},{"key":"e_1_3_3_62_2","doi-asserted-by":"publisher","DOI":"10.1007\/BF02296971"},{"key":"e_1_3_3_63_2","first-page":"644","article-title":"Tensor rank is NP-complete","volume":"4","author":"Johan H","year":"1990","unstructured":"Johan H. Tensor rank is NP-complete. J Algorithms 1990; 4: 644\u2013654.","journal-title":"J Algorithms"},{"key":"e_1_3_3_64_2","doi-asserted-by":"publisher","DOI":"10.1080\/10556789908805754"},{"key":"e_1_3_3_65_2","unstructured":"Song M Zou G Wan AT. Bootstrap model averaging. arXiv preprint arXiv:241205687 2024."},{"key":"e_1_3_3_66_2","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1996.10476934"},{"key":"e_1_3_3_67_2","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9868.2008.00693.x"},{"key":"e_1_3_3_68_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(17)31469-1"},{"key":"e_1_3_3_69_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(04)16257-0"},{"key":"e_1_3_3_70_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2014.05.013"},{"key":"e_1_3_3_71_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2006.02.024"},{"key":"e_1_3_3_72_2","doi-asserted-by":"publisher","DOI":"10.1006\/jmrb.1994.1037"},{"key":"e_1_3_3_73_2","doi-asserted-by":"publisher","DOI":"10.1002\/hbm.10062"},{"key":"e_1_3_3_74_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2015.10.019"},{"key":"e_1_3_3_75_2","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2020.1844211"},{"key":"e_1_3_3_76_2","volume-title":"Rey Auditory Verbal Learning Test: RAVLT: A Handbook","author":"Schmidt M","year":"1996","unstructured":"Schmidt M. Rey Auditory Verbal Learning Test: RAVLT: A Handbook. Torrance, CA: Western Psychological Services Los Angeles, 1996."},{"key":"e_1_3_3_77_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.nicl.2016.12.011"},{"key":"e_1_3_3_78_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-78095-7"}],"container-title":["Statistical Methods in Medical Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/09622802261424654","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/09622802261424654","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/09622802261424654","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T08:06:07Z","timestamp":1791446767000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/09622802261424654"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,3]]},"references-count":77,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["10.1177\/09622802261424654"],"URL":"https:\/\/doi.org\/10.1177\/09622802261424654","relation":{},"ISSN":["0962-2802","1477-0334"],"issn-type":[{"value":"0962-2802","type":"print"},{"value":"1477-0334","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,3]]}}}